hyper-exponential.com
Subscribe
Sign in
Home
Interviews
Archive
About
Latest
Top
How to do humans learn about values?
TLDR: Tan Zhi Xuan builds cooperative, theory-of-mind agents for safer AI, favoring human-like value learning and interpretable, model-based systems…
Jun 19
•
Mykhaylo Filipenko
Share this post
hyper-exponential.com
How to do humans learn about values?
Copy link
Facebook
Email
Notes
More
Thoughts on ASI - part 2: Giving up Control to AGI
TLDR: I believe that we have given up a lot of control to technology already and that this resulted in a net benefit for humanity. Giving up more…
Jun 2
•
Mykhaylo Filipenko
Share this post
hyper-exponential.com
Thoughts on ASI - part 2: Giving up Control to AGI
Copy link
Facebook
Email
Notes
More
May 2025
Interview with Agustin Covarrubias
TLDR: Agus runs Kairos. Kairos helps AI safety groups at university to be run efficiently. Kairos also runs SPAR - one of the best known AI safety…
May 9
•
Mykhaylo Filipenko
Share this post
hyper-exponential.com
Interview with Agustin Covarrubias
Copy link
Facebook
Email
Notes
More
April 2025
Thoughts on ASI - part 1: A spiritualist's view
TLDR: It's close to impossible to predict what awaits us "post singularity". Nevertheless, I try to lay out arguments that can give us hope to be…
Apr 24
•
Mykhaylo Filipenko
1
Share this post
hyper-exponential.com
Thoughts on ASI - part 1: A spiritualist's view
Copy link
Facebook
Email
Notes
More
Why are LLMs so Good at Generating Code?
An Interview with Georg Zoller
Apr 16
•
Mykhaylo Filipenko
Share this post
hyper-exponential.com
Why are LLMs so Good at Generating Code?
Copy link
Facebook
Email
Notes
More
There is hope for humanity ..
.. in one screenshot
Apr 4
•
Mykhaylo Filipenko
Share this post
hyper-exponential.com
There is hope for humanity ..
Copy link
Facebook
Email
Notes
More
Some thoughts on alignment ..
.. actually human alignment
Apr 2
•
Mykhaylo Filipenko
Share this post
hyper-exponential.com
Some thoughts on alignment ..
Copy link
Facebook
Email
Notes
More
March 2025
Safe AI with Singular Learning Theory ..
.. an interview with Jesse Hoogland from Timaeus
Mar 20
•
Mykhaylo Filipenko
Share this post
hyper-exponential.com
Safe AI with Singular Learning Theory ..
Copy link
Facebook
Email
Notes
More
February 2025
Can we have safer AI through certification?
An Interview with Jan Zawadzski from CertifAI
Feb 27
•
Mykhaylo Filipenko
Share this post
hyper-exponential.com
Can we have safer AI through certification?
Copy link
Facebook
Email
Notes
More
The right people at the right place ..
.. make the biggest difference
Feb 4
•
Mykhaylo Filipenko
Share this post
hyper-exponential.com
The right people at the right place ..
Copy link
Facebook
Email
Notes
More
January 2025
About bets and choices ..
.. and how they affect our lives
Jan 28
•
Mykhaylo Filipenko
1
Share this post
hyper-exponential.com
About bets and choices ..
Copy link
Facebook
Email
Notes
More
Dr. Jobst Heitzig: AGI with non-optimizer and how to start an AI safety lab in Germany?
TLDR: Dr.
Jan 8
•
Mykhaylo Filipenko
Share this post
hyper-exponential.com
Dr. Jobst Heitzig: AGI with non-optimizer and how to start an AI safety lab in Germany?
Copy link
Facebook
Email
Notes
More
Share
Copy link
Facebook
Email
Notes
More
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
